Changelog Master Feed

Fine-tuning vs RAG (Practical AI #238)

45 snips
Sep 6, 2023
Demetrios, from the MLOps Community, joins the podcast to discuss fine-tuning vs. retrieval augmented generation. They also talk about OpenAI Enterprise, the MLOps Community LLM survey results, and the orchestration and evaluation of generative AI workloads.
Ask episode
AI Snips
Chapters
Transcript
Episode notes
INSIGHT

Fine-tuning Misconceptions

  • Fine-tuning LLMs is often misunderstood compared to fine-tuning diffusion models like Stable Diffusion. - Retrieval augmented generation (RAG) better serves use cases like customizing responses based on company emails without costly GPU fine-tuning.
INSIGHT

Vector Databases as Stack Hero

  • Vector databases are the central component in the evolving LLM stack for tasks like semantic search. - Developer SDKs and monitoring tools build on top of vector databases to form the orchestration layer of generative AI systems.
INSIGHT

LLM Benchmarks Mislead Use Cases

  • Benchmarks for LLMs often mislead since top leaderboard models aren’t guaranteed best for specific use cases. - Evaluations must consider use-case specifics like latency, toxicity, and required capabilities beyond raw benchmark scores.
Get the Snipd Podcast app to discover more snips from this episode
Get the app